Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - VMAP_STACK support, allowing the kernel stacks to be allocated in the
   vmalloc space with a guard page for trapping stack overflows. One of
   the patches introduces THREAD_ALIGN and changes the generic
   alloc_thread_stack_node() to use this instead of THREAD_SIZE (no
   functional change for other architectures)

 - Contiguous PTE hugetlb support re-enabled (after being reverted a
   couple of times). We now have the semantics agreed in the generic mm
   layer together with API improvements so that the architecture code
   can detect between contiguous and non-contiguous huge PTEs

 - Initial support for persistent memory on ARM: DC CVAP instruction
   exposed to user space (HWCAP) and the in-kernel pmem API implemented

 - raid6 improvements for arm64: faster algorithm for the delta syndrome
   and implementation of the recovery routines using Neon

 - FP/SIMD refactoring and removal of support for Neon in interrupt
   context. This is in preparation for full SVE support

 - PTE accessors converted from inline asm to cmpxchg so that we can use
   LSE atomics if available (ARMv8.1)

 - Perf support for Cortex-A35 and A73

 - Non-urgent fixes and cleanups

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (75 commits)
  arm64: cleanup {COMPAT_,}SET_PERSONALITY() macro
  arm64: introduce separated bits for mm_context_t flags
  arm64: hugetlb: Cleanup setup_hugepagesz
  arm64: Re-enable support for contiguous hugepages
  arm64: hugetlb: Override set_huge_swap_pte_at() to support contiguous hugepages
  arm64: hugetlb: Override huge_pte_clear() to support contiguous hugepages
  arm64: hugetlb: Handle swap entries in huge_pte_offset() for contiguous hugepages
  arm64: hugetlb: Add break-before-make logic for contiguous entries
  arm64: hugetlb: Spring clean huge pte accessors
  arm64: hugetlb: Introduce pte_pgprot helper
  arm64: hugetlb: set_huge_pte_at Add WARN_ON on !pte_present
  arm64: kexec: have own crash_smp_send_stop() for crash dump for nonpanic cores
  arm64: dma-mapping: Mark atomic_pool as __ro_after_init
  arm64: dma-mapping: Do not pass data to gen_pool_set_algo()
  arm64: Remove the !CONFIG_ARM64_HW_AFDBM alternative code paths
  arm64: Ignore hardware dirty bit updates in ptep_set_wrprotect()
  arm64: Move PTE_RDONLY bit handling out of set_pte_at()
  kvm: arm64: Convert kvm_set_s2pte_readonly() from inline asm to cmpxchg()
  arm64: Convert pte handling from inline asm to using (cmp)xchg
  arm64: neon/efi: Make EFI fpsimd save/restore variables static
  ...

1 files changed, 38 insertions, 2 deletions

diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 2386b26c0712..713561e5bcab 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -23,15 +23,16 @@
 
 #include <linux/kernel_stat.h>
 #include <linux/irq.h>
+#include <linux/memory.h>
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/irqchip.h>
 #include <linux/seq_file.h>
+#include <linux/vmalloc.h>
 
 unsigned long irq_err_count;
 
-/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */
-DEFINE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack) __aligned(16);
+DEFINE_PER_CPU(unsigned long *, irq_stack_ptr);
 
 int arch_show_interrupts(struct seq_file *p, int prec)
 {
@@ -50,8 +51,43 @@ void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
 	handle_arch_irq = handle_irq;
 }
 
+#ifdef CONFIG_VMAP_STACK
+static void init_irq_stacks(void)
+{
+	int cpu;
+	unsigned long *p;
+
+	for_each_possible_cpu(cpu) {
+		/*
+		* To ensure that VMAP'd stack overflow detection works
+		* correctly, the IRQ stacks need to have the same
+		* alignment as other stacks.
+		*/
+		p = __vmalloc_node_range(IRQ_STACK_SIZE, THREAD_ALIGN,
+					 VMALLOC_START, VMALLOC_END,
+					 THREADINFO_GFP, PAGE_KERNEL,
+					 0, cpu_to_node(cpu),
+					 __builtin_return_address(0));
+
+		per_cpu(irq_stack_ptr, cpu) = p;
+	}
+}
+#else
+/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */
+DEFINE_PER_CPU_ALIGNED(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack);
+
+static void init_irq_stacks(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack, cpu);
+}
+#endif
+
 void __init init_IRQ(void)
 {
+	init_irq_stacks();
 	irqchip_init();
 	if (!handle_arch_irq)
 		panic("No interrupt controller found.");